Google
Google

Gemini 2.5 Flash

Model ID:gemini-2.5-flash
2025-06-17Proprietary Model
API
OverallNo.25
PopularityNo.12

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).

Knowledge Cutoff
2025-01-31

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory
1.0MIN66KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words
$0.3IN$2.5OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

AI Performance Evaluation

Arena Overall Score
1411
±3
As of 2026-04-02
Overall Rank
No.77
105,291 Votes
Arena by Ability
Hard Prompts
1420±4No.87
Expert Knowledge
1428±8No.77
Instruction Following
1403±4No.69
Conversation Memory
1403±5No.91
Creative
1398±6No.53
Coding
1425±5No.118
Math
1409±7No.79
Arena by Occupation
Creative Writing
1405±5No.55
Social Sciences
1428±5No.75
Media
1389±5No.63
Business
1398±5No.92
Healthcare
1424±8No.92
Legal
1427±8No.64
Software
1423±4No.106
Mathematics
1421±8No.68
Arena Image Score
1155
±3
As of 2026-03-26
Overall Rank
No.12
701,554 Votes
Arena by Image Category
Art
1148±5No.17
Cartoon
1151±4No.13
Photorealistic
1163±4No.10
Portraits
1176±5No.8
Text Rendering
1154±4No.13
3D Modeling
1140±6No.20
Commercial Design
1152±4No.14
Reasoning Ability
AA Intelligence Index
27%↓12%
MMLU-Pro
83%↑1%
GPQA Diamond
79%↓3%
HLE
11%↓6%
Math
AA Math Index
73%↓1%
MATH-500
98%↑4%
AIME 2024
82%↑23%
AIME 2025
73%↓1%
Coding Ability
AA Coding Index
22%↓14%
LiveCodeBench
70%↑4%
SciCode
39%↓3%
TerminalBench
14%↓20%
Instruction Following
IFBench
50%↓7%
환각률 (HHEM)
7.8%↓3%
사실 일관성 (HHEM)
92%↑3%
Long Context
AA-LCR
62%↓2%
Agentic AI Ability
TAU2
32%↓40%
Speed
Standard Mode
213tok/sec↑135
First Output 0.44s
Artificial Analysis
Reasoning Mode
229tok/sec↑156
First Output 11.89s
Artificial Analysis